Abstract
Since 2013, the São Francisco River has being through a low hydraulicity period. In other words, the rain intensity is below average. Consequently, it has being necessary to operate at a minimal flow rate. It is far below the ones established at the operation licence, which is 1300 m\(^3\)/s. Due to this hydraulic crisis, the actual operational flow rate is 700 m\(^3\)/s at São Francisco River, characterizing this situation as critical. In this work, it was proposed to use Reservoir Computing (RC), Long Short Term Memory (LSTM) and Deep Learning to predict Sobradinho’s flow rate for 1, 2 and 3 months ahead using macroclimatic variables. After having the results for each one of them, a comparison was made and statistical tests where executed for evaluation.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Valença, M.J.S., Ludermir, T.B., Valença, A., Vasconcelos, I.: Sistema de Apoio a Decisão para a Operação Hidráulica de Sobradinho Incorporando Tendências Macro-Climáticas Utilizando Redes Neurais (2009)
Brooks, K.N., Ffolliott, P.F., Magner, J.A.: Hydrology and the Management of Watersheds, 3 edn. (2003)
Valença, M.J.S.: Proposta de Alerta Ambiental baseada na Previsão de Volumes Máximos Afluentes ao reservatório de Sobradinho
Agência Nacional de Águas (ANA): http://www2.ana.gov.br/Paginas/servicos/saladesituacao/v2/saofrancisco.aspx/
What is Air Temperature? https://www.fondriest.com/news/airtemperature.htm
Mendonça, F., Dubreuil, V.: Termografiada superfície e temperatura do ar na rmc (regiãometropolitana de curitiba/pr). Editora UFPR, pp. 25–35 (2005)
Cavalcanti, E.P., de Silva, V.P.R., de Sousa, A.S.F.: Programa computacional para a estimativa da temperatura do ar para a região nordeste do Brazil. Revista Brasileira de Engenharia Agrícola e Ambiental, pp. 140–147 (2006)
Embrapa: http://www.agencia.cnptia.embrapa.br/Agencia22/AG01/arvore/AG01_79_24112005115223.html
Bomventi, T.N., Wainer, I.E.K.C., Taschetto, A.S.: Relação entre a radiação de onda longa, precipitação e temperatura da superfície do mar no oceano atlântico tropical. Revista Brasileira de Geofísica 24, 513–524, 12 2006. http://www.scielo.br/scielo.php?script=sci_arttext&pid=S0102-261X2006000400005&nrm=iso
Susskind, J., Molnar, G., Iredell, L.: Contributions to Climate Research Using the AIRS Science Team Version-5 Products (2011)
de Stefano Ermenegildo, L.F., Pereira, S.B., Arai, F.K., Rosa, D.B.C.J.: Vazão específica e precipitação média na bacia do ivinhema. Dourados, pp. 428–432 (2012)
Tucci, C.E.M.: Hidrologia: ciência e aplicação. ABRH, 3 edn. (2002)
Rodrigues, A.L.: Informações macroclimáticas aplicadas na previsão de vazões. São Paulo (2016)
Valença, M.J.S.: Fundamentos das Redes Neurais. Livro Rápido, Brazil (2016)
Ye Rena, P.N., Suganthana, N.S., Amaratungac, G.: Random vector functional link network for short-term electricity load demand forecasting. Inf. Sci. 367–368, 1078–1093 (2016)
Ferreira, A.A., Ludermir, T.B.: Um Método para Design e Treinamento de Reservoir Computing Aplicado à Previsão de Séries Temporais. Pernambuco (2011)
Jaeger, H.: The “echo state” approach to analyzing and training recurrent neural networks (2011)
Mass, W., Natschläger, T., Markram, H.: Real-time computing without stable states: a new framework for neural computation based on perturbations. Neural Comput. 14, 2531–2560 (2002)
Verstraeten, D.: Reservoir computing: computation with dynamical systems. Belgium (2009)
A Gentle Introduction to Backpropagation Through Time. https://machinelearningmastery.com/gentle-introduction-backpropagation-time/
Time Series Prediction with LSTM Recurrent Neural Networks in Python with Keras. https://machinelearningmastery.com/time-series-prediction-lstm-recurrent-neural-networks-python-keras/
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 1735–1780 (1997)
Deng, L., Yu, D.: Deep Learning Methods and Applications, Foundations and Trends in Signal Processing, 7th edn. Now Publishers Inc., Boston (2014)
Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge (2016). http://www.deeplearningbook.org
National Oceanic and Atmospheric Administration (NOAA). http://www.noaa.gov/
Eletrobras. http://eletrobras.com/pt/Paginas/home.aspx
Companhia Hidroelétrica do São Francisco (Chesf). http://www.chesf.gov.br
Wang, L., Fu, X.: Data Mining with Computational Intelligence. Springer, Heidelberg (2005). https://doi.org/10.1007/3-540-28803-1
Hartshorn, S.: Linear Regression And Correlation: A Beginner’s Guide, 1st edn. Amazon Digital Services LLC, Seattle (2017)
Hartshorn, S.: Machine Learning With Random Forests And Decision Trees: A Visual Guide For Beginners, 1st edn. Amazon Digital Services LLC, Seattle (2016)
Kok Keong Teo, L.W., Lin, Z.: Wavelet packet multi-layer perceptron for chaotic time series prediction: effects of weight initialization. In: International Conference on Computational Science, vol. 2074, pp. 310–317, 7 2001
Keras. https://keras.io/
Python. https://www.python.org/
Kingma, D.P., Ba, J.L.: Adam: a method for stochastic optimization. In: International Conference for Learning Representations (2014)
A simple deep learning model for stock price prediction using TensorFlow. https://medium.com/mlreview/a-simple-deep-learning-model-for-stock-price-prediction-using-tensorflow-30505541d877
Tensorflow. https://www.tensorflow.org/
Moreno, A.M., Juristo, N.: Basics of Software Engineering Experimentation. Kluwer Academic Publisher, Dordrecht (2001)
Venables, W.N., Smith, D.M., the R Core Team: An Introduction to R. Network Theory Ltd, Hershey (2009)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Santos, B., Aguiar, B., Valença, M. (2018). Applying Macroclimatic Variables to Improve Flow Rate Forecasting Using Neural Networks Techniques. In: Cheng, L., Leung, A., Ozawa, S. (eds) Neural Information Processing. ICONIP 2018. Lecture Notes in Computer Science(), vol 11305. Springer, Cham. https://doi.org/10.1007/978-3-030-04221-9_6
Download citation
DOI: https://doi.org/10.1007/978-3-030-04221-9_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-04220-2
Online ISBN: 978-3-030-04221-9
eBook Packages: Computer ScienceComputer Science (R0)